Unsupervised mapping and semantic user localisation from first-person monocular video

Download PDF
Open Webpage

Tamás Süveges, Stephen J. McKenna

Published: 01 Jan 2025, Last Modified: 07 Nov 2025Pattern Recognit. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Unsupervised map learning and localisation from first-person (wearable) video.•Proposed map representation using place graphs and view graphs.•Evaluation of online mapping and localisation using two datasets.•Demonstrated effectiveness of hierarchical map representation.